How to Setup Blender MCP with Claude, Codex & Gemini CLI

In this video, I’ll show you how to set up Blender’s official MCP server and connect it to Claude Desktop, Codex, and Gemini CLI so you can control Blender using natural language. We’ll walk through installing the Blender MCP add-on, cloning the MCP server repository, configuring each AI client, and testing it inside Blender with a few practical examples. I also briefly cover my experience testing the local LLM option using Qwen. What You’ll Need 🔹 Blender 5.1 https://www.blender.org/download/ 🔹 Python https://www.python.org/downloads/ 🔹 Node.js https://nodejs.org/ 🔹 Git https://git-scm.com/downloads 🔹 UV (Python package manager) https://docs.astral.sh/uv/getting-sta... AI Clients Covered 🔹 Claude Desktop https://www.anthropic.com/claude 🔹 OpenAI Codex CLI https://developers.openai.com/ 🔹 Gemini CLI https://github.com/google-gemini/gemi... Blender MCP Resources 🔹 Official Blender MCP Documentation https://www.blender.org/lab/mcp-server/ Chapters 00:00 Intro 00:22 Install Blender MCP Add-on 00:51 Clone the MCP Server Repo 01:16 Run the Server with UV 01:45 Setup Codex 02:14 Codex Test - Golden Sphere 02:47 Setup Gemini CLI 03:13 Gemini Test - Golden Sphere 03:55 Setup Claude Desktop 04:33 Claude Test - Planet Earth 05:15 Gemini Test - Medieval Village 05:49 Local LLM Notes 06:31 Final Thoughts My Thoughts This is a really interesting step forward for AI-assisted 3D workflows. While it won’t replace traditional Blender skills, it can already be very useful for prototyping, scene layout, repetitive tasks, and experimentation. If you found the video helpful, feel free to like, subscribe, and leave a comment with which setup worked best for you. #blender #mcp #ai #claude #gemini #openai #3dmodeling #gamedev